استفاده از مدل ترکیبی برای بهبود عملکرد روش‌های ANN، ANFIS و SVR در تخمین پارامترهای BOD و COD پساب تصفیه‌خانه فاضلاب

نوع مقاله : مقاله پژوهشی

نویسندگان

گروه عمران آب، دانشکده عمران، دانشگاه تبریز، تبریز، ایران

چکیده

دست‌یابی به طراحی دقیق و راهبری صحیح تصفیه‌خانه‌های فاضلاب از جمله چالش‌های مهم در صنعت آب و فاضلاب به شمار می‌آید. مدل‌های عددی به دلیل نیاز به داده‌های فراوان، زمان‌بر بوده و صرفه اقتصادی ندارند. بنابراین در این مطالعه، عملکرد تصفیه‌خانه فاضلاب تبریز با استفاده از مدل‌های جعبه‌سیاه هوش مصنوعی شامل شبکه عصبی مصنوعی (ANN)، سیستم استنتاج تطبیقی عصبی-فازی (ANFIS)، رگرسیون بردار پشتیبان (SVR) و مدل جعبه‌سیاه کلاسیک خودهمبسته تفاضلی با میانگین متحرک (ARIMA) براساس داده‌های روزانه سال‌های 1395-1396 مورد بررسی قرار گرفته ‌است. جهت تعیین پارامترهای ورودی از معیار ضریب همبستگی (CC) استفاده شد که پارامترهای اکسیژن مورد نیاز بیولوژیکی (BOD)، اکسیژن مورد نیاز شیمیایی (COD) ، مواد جامد معلق (TSS)، pH ورودی به تصفیه‌خانه در زمان t و BOD وCOD پساب خروجی از تصفیه‌خانه در یک گام زمانی قبل (t-1) با بیشترین مقادیر CC به عنوان ورودی انتخاب گردیدند. BOD وCOD پساب خروجی نیز به عنوان پارامترهای خروجی مدل‌های هوش مصنوعی در نظرگرفته شده‌اند. همچنین برای بهبود عملکرد مدل‌سازی، روش ترکیب مدل با استفاده از خروجی مدل‌های منفرد مذکور، به عنوان یک روش پس‌پردازش، بکار گرفته‌ شده ‌است. ترکیب مدل به سه روش میانگین‌گیری خطی ساده، میانگین‌گیری خطی وزن‌دار و میانگین‌گیری غیر خطی با استفاده از شبکه عصبی مصنوعی انجام گرفته ‌است. نتایج حاکی از آن است که بکارگیری مدل‌های غیرخطی بهتر از مدل خطی ARIMA بوده و مدل SVR بالاترین مقدار ضریب تبیین (DC) را ارائه کرده ‌است. همچنین استفاده از مدل‌های ترکیبی و به ویژه مدل ترکیبی غیرخطی با شبکه عصبی مصنوعی باعث افزایش عملکرد مدل‌سازی  تا 15% در مرحله صحت‌سنجی می‌شود.

کلیدواژه‌ها

موضوعات

عنوان مقاله [English]

Using Ensemble Model to Improve ANN, ANFIS, SVR Models in Predicting Effluent BOD and COD

نویسندگان [English]

  • Parisa Asghari
  • Vahid Nourani
  • Elnaz Sharghi
  • nazanin behfar
Department of Water Resources Engineering, Faculty of Civil Engineering, University of Tabriz, Tabriz, Iran
چکیده [English]

In this study, black box artificial intelligence models (AI) including feed-forward neural network (FFNN), support vector regression (SVR), and adaptive neuro-fuzzy inference system (ANFIS) were used to predict effluent biological oxygen demand (BODeff) and chemical oxygen demand (CODeff) of Tabriz wastewater treatment plant (WWTP) using the daily data collected from 2016 to 2018. In addition, the autoregressive integrated moving average (ARIMA) linear model was used to predict BODeff and CODeff parameters to compare the linear and non-linear models' abilities in complex processes prediction. To improve the prediction of BODeff and CODeff parameters, the data post-processing ensemble method was also used. The input data set included daily influent BOD, COD, total suspended solids (TSS), pH at the current time (t), and BODeff and CODeff at the previous time (t-1) and the output data included BODeff and CODeff at t. The results of the single models indicated that the SVR model provides better results than the other single models. In ensemble modeling, simple and weighted linear averaging, and neural network ensemble methods were applied to enhance the performance of the single AI models. The results indicated that using ensemble models could increase the prediction accuracy up to 15% at the verification phase.

کلیدواژه‌ها [English]

  • Soft computing
  • Artificial intelligence
  • ARIMA linear model
  • Ensemble
  • Wastewater treatment plant

مراجع

  1. S. Mjalli, S. Al-Asheh, H. Alfadala, Use of artificial neural network black-box modeling for the prediction of wastewater treatment plants performance, Journal of Environmental Management, 83(3) (2007) 329-338.
  2. Arzate, S. Pfister, C. Oberschelp, J.A. Sánchez-Pérez, Environmental impacts of an advanced oxidation process as tertiary treatment in a wastewater treatment plant, Science of The Total Environment, 694 (2019) 133572.
  3. M. Hamed, M.G. Khalafallah, E.A. Hassanien, Prediction of wastewater treatment plant performance using artificial neural networks, Environmental Modelling & Software, 19(10) (2004) 919-928.
  4. Owa, Water pollution: sources, effects, control and management, Mediterranean journal of social sciences, 4(8) (2013) 65.
  5. D. Salas, Applied modeling of hydrologic time series, Water Resources Publication, 1980.
  6. Nourani, M. Parhizkar, Conjunction of SOM-based feature extraction method and hybrid wavelet-ANN approach for rainfall–runoff modeling, Journal of Hydroinformatics, 15(3) (2013) 829-848.
  7. .A. Nadiri, E. Fijani, F.T.-C. Tsai, A. Asghari Moghaddam, Supervised committee machine with artificial intelligence for prediction of fluoride concentration, Journal of Hydroinformatics, 15(4) (2013) 1474-1490.
  8. W. Chan, G.H. Huang, Artificial intelligence for management and control of pollution minimization and mitigation processes, Engineering applications of artificial intelligence, 16(2) (2003) 75-90.
  9. F. Hamoda, I.A. Al-Ghusain, A.H. Hassan, Integrated wastewater treatment plant performance evaluation using artificial neural networks, Water Science and Technology, 40(7) (1999) 55-65.
  10. Gontarski, P. Rodrigues, M. Mori, L. Prenem, Simulation of an industrial wastewater treatment plant using artificial neural networks, Computers & Chemical Engineering, 24(2-7) (2000) 1719-1723.
  11. Dogan, A. Ates, E.C. Yilmaz, B. Eren, Application of artificial neural networks to estimate wastewater treatment plant inlet biochemical oxygen demand, Environmental progress, 27(4) (2008) 439-446.
  12. Sharghi, V. Nourania, A. AliAshrafia, H. Gökçekuşb, Monitoring effluent quality of wastewater treatment plant by clustering based artificial neural network method, DESALINATION AND WATER TREATMENT, 164 (2019) 86-97.
  13. S. Nasr, M.A. Moustafa, H.A. Seif, G. El Kobrosy, Application of Artificial Neural Network (ANN) for the prediction of EL-AGAMY wastewater treatment plant performance-EGYPT, Alexandria engineering journal, 51(1) (2012) 37-43.
  14. -Y. Pai, Gray and neural network prediction of effluent from the wastewater treatment plant of industrial park using influent quality, Environmental Engineering Science, 25(5) (2008) 757-766.
  15. Ö. Çinar, New tool for evaluation of performance of wastewater treatment plant: artificial neural network, Process Biochemistry, 40(9) (2005) 2980-2984.
  16. Heddam, H. Lamda, S. Filali, Predicting effluent biochemical oxygen demand in a wastewater treatment plant using generalized regression neural network based approach: a comparative study, Environmental Processes, 3(1) (2016) 153-165.
  17. Yazdani, A. Khoshhal, N.S. Mousavi, Evaluating the performance of a sequencing batch reactor (SBR) for sanitary wastewater treatment Using Artificial Neural Network (ANN), Environmental Progress & Sustainable Energy, (2020) e13438.
  18. Yel, S. Yalpir, Prediction of primary treatment effluent parameters by Fuzzy Inference System (FIS) approach, Procedia Computer Science, 3 (2011) 659-665.
  19. Wan, M. Huang, Y. Ma, W. Guo, Y. Wang, H. Zhang, W. Li, X. Sun, Prediction of effluent quality of a paper mill wastewater treatment using an adaptive network-based fuzzy inference system, Applied Soft Computing, 11(3) (2011) 3238-3246.
  20. -Y. Pai, S. Wang, C. Chiang, H. Su, L. Yu, P. Sung, C. Lin, H. Hu, Improving neural network prediction of effluent from biological wastewater treatment plant of industrial park using fuzzy learning approach, Bioprocess and biosystems engineering, 32(6) (2009) 781-790.
  21. Pai, P. Yang, S. Wang, M. Lo, C. Chiang, J. Kuo, H. Chu, H. Su, L. Yu, H. Hu, Predicting effluent from the wastewater treatment plant of industrial park based on fuzzy network and influent quality, Applied Mathematical Modelling, 35(8) (2011) 3674-3684.
  22. Guo, K. Jeong, J. Lim, J. Jo, Y.M. Kim, J.-p. Park, J.H. Kim, K.H. Cho, Prediction of effluent concentration in a wastewater treatment plant using machine learning models, Journal of Environmental Sciences, 32 (2015) 90-101.
  23. Granata, S. Papirio, G. Esposito, R. Gargano, G. De Marinis, Machine learning algorithms for the forecasting of wastewater quality indicators, Water, 9(2) (2017) 105.
  24. S. Zaghloul, R.A. Hamza, O.T. Iorhemen, J.H. Tay, Comparison of adaptive neuro-fuzzy inference systems (ANFIS) and support vector regression (SVR) for data-driven modelling of aerobic granular sludge reactors, Journal of Environmental Chemical Engineering, 8(3) (2020) 103742.
  25. M. Bates, C.W. Granger, The combination of forecasts, Journal of the Operational Research Society, 20(4) (1969) 451-468.
  26. Dickinson, Some statistical results in the combination of forecasts, Journal of the Operational Research Society, 24(2) (1973) 253-260.
  27. Dickinson, Some comments on the combination of forecasts, Journal of the Operational Research Society, 26(1) (1975) 205-210.
  28. D. Thompson, How to improve accuracy by combining independent forecasts, Monthly Weather Review, 105(2) (1977) 228-229.
  29. T. Clemen, Combining forecasts: A review and annotated bibliography, International journal of forecasting, 5(4) (1989) 559-583.
  30. Y. Shamseldin, K.M. O'Connor, G. Liang, Methods for combining the outputs of different rainfall–runoff models, Journal of Hydrology, 197(1-4) (1997) 203-229.
  31. Xiong, A.Y. Shamseldin, K.M. O'connor, A non-linear combination of the forecasts of rainfall-runoff models by the first-order Takagi–Sugeno fuzzy system, Journal of hydrology, 245(1-4) (2001) 196-217.
  32. P. Zhang, Time series forecasting using a hybrid ARIMA and neural network model, Neurocomputing, 50 (2003) 159-175.
  33. Li, A. Sankarasubramanian, Reducing hydrologic model uncertainty in monthly streamflow predictions using multimodel combination, Water Resources Research, 48(12) (2012).
  34. Sharghi, V. Nourani, N. Behfar, Earthfill dam seepage analysis using ensemble artificial intelligence based modeling, Journal of Hydroinformatics, 20(5) (2018) 1071-1084.
  35. S. Govindaraju, Artificial neural networks in hydrology. II: hydrologic applications, Journal of Hydrologic Engineering, 5(2) (2000) 124-137.
  36. Nourani, An emotional ANN (EANN) approach to modeling rainfall-runoff process, Journal of Hydrology, 544 (2017) 267-277.
  37. Farhoudi, S. Hosseini, M. Sedghi-Asl, Application of neuro-fuzzy model to estimate the characteristics of local scour downstream of stilling basins, Journal of hydroinformatics, 12(2) (2010) 201-211.
  38. Abraham, Adaptation of fuzzy inference system using neural learning, in: Fuzzy systems engineering, Springer, 2005, pp. 53-83.
  39. -S.R. Jang, C.-T. Sun, E. Mizutani, Neuro-fuzzy and soft computing-a computational approach to learning and machine intelligence [Book Review], IEEE Transactions on automatic control, 42(10) (1997) 1482-1484.
  40. -c. Wang, D.-m. Xu, K.-w. Chau, S. Chen, Improved annual rainfall-runoff forecasting using PSO–SVM model based on EEMD, Journal of Hydroinformatics, 15(4) (2013) 1377-1390.
  41. N. Vapnik, An overview of statistical learning theory, IEEE transactions on neural networks, 10(5) (1999) 988-999.
  42. H. Haghiabi, H.M. Azamathulla, A. Parsaie, Prediction of head loss on cascade weir using ANN and SVM, ISH Journal of Hydraulic Engineering, 23(1) (2017) 102-110.
  43. F. Ansley, An algorithm for the exact likelihood of a mixed autoregressive-moving average process, Biometrika, 66(1) (1979) 59-65.
  44. Nourani, M. Komasi, A. Mano, A multivariate ANN-wavelet approach for rainfall–runoff modeling, Water resources management, 23(14) (2009) 2877.
  45. Haykin, Neural networks: a comprehensive foundation, Prentice-Hall, Inc., 2007.
  46. Noori, A. Karbassi, A. Moghaddamnia, D. Han, M. Zokaei-Ashtiani, A. Farokhnia, M.G. Gousheh, Assessment of input variables determination on the SVM model performance using PCA, Gamma test, and forward selection techniques for monthly stream flow prediction, Journal of Hydrology, 401(3-4) (2011) 177-189.
نشریه مهندسی عمران امیرکبیر
دوره 53، شماره 11
بهمن 1400
صفحه 4683-4702

فایل ها

هم رسانی

ارجاع به این مقاله

آمار